© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216210
    Prev
    Next
    INDEX
    Explanations

    sessionmaker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    投影
    0.46
    ﻳ
    0.40
    шкина
    0.39
    логов
    0.38
     ऑलरेडी
    0.38
    级别
    0.38
    ラボ
    0.38
     projecting
    0.38
    Bright
    0.38
    䚺
    0.38
    POSITIVE LOGITS
    稱
    0.40
     mars
    0.37
     click
    0.36
     Click
    0.36
     ところ
    0.36
     Mars
    0.35
     refe
    0.35
    zym
    0.35
     cho
    0.35
    édon
    0.35
    Activations Density 0.000%

    No Known Activations